agent browser
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
- Installs
- 1.2K
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/am-will/codex-skills --skill agent-browser- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads agent browser automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Agent Browser
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
Installation
npm recommended
npm install -g agent-browser
agent-browser install
agent-browser install --with-deps
From Source
git clone https://github.com/vercel-labs/agent-browser
cd agent-browser
pnpm install
pnpm build
agent-browser install
Quick Start
agent-browser open example.com
agent-browser snapshot
agent-browser click @e2
agent-browser fill @e3 "test@example.com"
agent-browser get text @e1
agent-browser screenshot page.png
agent-browser close
Using Real Chrome Profile (for OAuth/Logged-in Sessions)
For sites requiring Google/Discord/etc login (like star-swap.com):
Method 1: Launch Chrome with custom profile, connect via CDP
# Terminal 1: Launch Chrome with your real profile and remote debugging
google-chrome --remote-debugging-port=9222 --user-data-dir=/home/willr/.config/google-chrome/Default &
# Terminal 2: Connect agent-browser to that Chrome instance
agent-browser --cdp 9222 open "https://star-swap.com"
agent-browser --cdp 9222 snapshot -i
agent-browser --cdp 9222 click e2
# This reuses your existing Google session - no re-login needed!
# Works for: Google OAuth, Discord OAuth, any site you're logged into in Chrome
Method 2: Session persistence (first-time manual login)
# First time: headed mode, login manually
agent-browser --headed --session starswap open "https://star-swap.com"
# Complete Google OAuth manually in the browser window
# Close when done
# Future runs: cookies persist!
agent-browser --session starswap open "https://star-swap.com"
# Already logged in automatically
am.will.ryan Chrome profile: /home/willr/.config/google-chrome/Default
Core Commands
Navigation
agent-browser open <url>
agent-browser back
agent-browser forward
agent-browser reload
Interaction
agent-browser click <sel>
agent-browser dblclick <sel>
agent-browser focus <sel>
agent-browser type <sel> <text>
agent-browser fill <sel> <text>
agent-browser clear <sel>
agent-browser press <key>
agent-browser keydown <key>
agent-browser keyup <key>
agent-browser hover <sel>
agent-browser select <sel> <val>
agent-browser check <sel>
agent-browser uncheck <sel>
agent-browser drag <src> <tgt>
agent-browser upload <sel> <files>
Extraction and Info
agent-browser snapshot
agent-browser get text <sel>
agent-browser get html <sel>
agent-browser get value <sel>
agent-browser get attr <sel> <attr>
agent-browser get title
agent-browser get url
agent-browser get count <sel>
agent-browser get box <sel>
agent-browser screenshot [path]
agent-browser pdf <path>
Check State
agent-browser is visible <sel>
agent-browser is enabled <sel>
agent-browser is checked <sel>
Find Elements
- agent-browser find role <role> <action> [value]
- agent-browser find text <text> <action>
- agent-browser find label <label> <action> [value]
- agent-browser find placeholder <ph> <action> [value]
- agent-browser find alt <text> <action>
- agent-browser find title <text> <action>
- agent-browser find testid <id> <action> [value]
Actions include click, fill, check, hover, and text.
Wait and Timing
agent-browser wait <selector>
agent-browser wait <ms>
agent-browser wait --text "Welcome"
agent-browser wait --url "**/dash"
agent-browser wait --load networkidle
Advanced Control
agent-browser scroll <dir> [px]
agent-browser scrollintoview <sel>
agent-browser eval <js>
agent-browser mouse move <x> <y>
agent-browser cookies
agent-browser storage local
agent-browser tab new [url]
agent-browser frame <sel>
agent-browser dialog accept [text]
Sessions
Run multiple isolated browser instances.
agent-browser --session agent1 open site-a.com
agent-browser --session agent2 open site-b.com
Snapshot Options
The snapshot command supports filtering to reduce output size.
- agent-browser snapshot -i
- agent-browser snapshot -c
- agent-browser snapshot -d 3
- agent-browser snapshot -s "#main"
Selectors and Refs
Refs provide deterministic element selection from snapshots. Use the @ref syntax.
agent-browser snapshot
agent-browser click @e2
Agent Mode
Use --json for machine readable output.
agent-browser snapshot --json
Optimal AI Workflow
- Navigate with agent-browser open <url>
- Observe with agent-browser snapshot -i --json
- Act with @ref from the snapshot
- Verify with agent-browser snapshot
Troubleshooting
- If the command is not found on Linux ARM64, use the full path in the bin folder.
- If an element is not found, use snapshot to find the correct ref.
- If the page is not loaded, add a wait command after navigation.
- Use --headed to see the browser window for debugging.
Options
- --session <name> uses an isolated session.
- --json provides JSON output.
- --full takes a full page screenshot.
- --headed shows the browser window.
- --timeout sets the command timeout in milliseconds.
Notes
- Refs are stable per page load but change on navigation.
- Always snapshot after navigation to get new refs.
- Use fill instead of type for input fields to ensure existing text is cleared.
FAQ
What does the agent browser skill do?
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
How do I install agent browser?
Run npx skills add https://github.com/am-will/codex-skills --skill agent-browser in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/agent-browser/ (personal) or .claude/skills/agent-browser/ (project).
Which AI agents can use agent browser?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is agent browser safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains agent browser?
It is published by am-will in am-will/codex-skills. It has 1,161 recorded installs.
More from am-will/codex-skills
frontend-design
am-will/codex-skills
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
frontend responsive design standards
am-will/codex-skills
Build responsive, mobile-first layouts using fluid containers, flexible units, media queries, and touch-friendly design that works across all screen sizes. Use this skill when creating or modifying UI layouts, responsive grids, breakpoint styles, mobile navigation, or any interface that needs to adapt to different screen sizes. Apply when working with responsive CSS, media queries, viewport settings, flexbox/grid layouts, mobile-first styling, breakpoint definitions (mobile, tablet, desktop), touch target sizing, relative units (rem, em, %), image optimization for different screens, or testing layouts across multiple devices. Use for any task involving multi-device support, responsive design patterns, or adaptive layouts.
context7
am-will/codex-skills
Fetch up-to-date library documentation via Context7 CLI. Use PROACTIVELY when: (1) Working with ANY external library (React, Next.js, Supabase, etc.) (2) User asks about library APIs, patterns, or best practices (3) Implementing features that rely on third-party packages (4) Debugging library-specific issues (5) Need current documentation beyond training data cutoff (6) AND MOST IMPORTANTLY, when you are installing dependencies, libraries, or frameworks you should ALWAYS check the docs to see what the latest versions are. Do not rely on outdated knowledge. Always prefer this over guessing library APIs or using outdated knowledge.
planner
am-will/codex-skills
Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: "make a plan", "create a plan", "plan this out", "plan the implementation", "help me plan", "design a plan", "draft a plan", "write a plan", "outline the steps", "break this down into tasks", "what's the plan for", or any similar planning request. Also triggers on explicit "/planner" or "/plan" commands.
read-github
am-will/codex-skills
Read and search GitHub repository documentation via gitmcp.io MCP service. WHEN TO USE: - User provides a GitHub URL - User mentions a specific repo in owner/repo format - User asks "what does this repo do?", "read the docs for X repo", or similar - User wants to search code or docs within a repo
parallel-task
am-will/codex-skills
Only to be triggered by explicit /parallel-task commands.
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由；/page/ 是妙搭应用，非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token 也按资源路径和 token 路由，不回退 WebFetch。不负责：文档内容编辑（走 lark-doc）、表格/Base 表内数据操作（走 lark-sheets/lark-base）、知识空间节点/成员管理（走 lark-wiki）、原生 Markdown 文件读写/patch/diff（走 lark-markdown）。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。